{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/deep-convolutional-denoising-of-low-light","title":"Deep Convolutional Denoising of Low-Light Images","arxiv_id":"1701.01687","date":"2017-01-06","proceeding":null,"authors":["Tal Remez","Or Litany","Raja Giryes","Alex M. Bronstein"],"abstract":"Poisson distribution is used for modeling noise in photon-limited imaging.\nWhile canonical examples include relatively exotic types of sensing like\nspectral imaging or astronomy, the problem is relevant to regular photography\nnow more than ever due to the booming market for mobile cameras. Restricted\nform factor limits the amount of absorbed light, thus computational\npost-processing is called for. In this paper, we make use of the powerful\nframework of deep convolutional neural networks for Poisson denoising. We\ndemonstrate how by training the same network with images having a specific peak\nvalue, our denoiser outperforms previous state-of-the-art by a large margin\nboth visually and quantitatively. Being flexible and data-driven, our solution\nresolves the heavy ad hoc engineering used in previous methods and is an order\nof magnitude faster. We further show that by adding a reasonable prior on the\nclass of the image being processed, another significant boost in performance is\nachieved.","url_abs":"http://arxiv.org/abs/1701.01687v1","url_pdf":"http://arxiv.org/pdf/1701.01687v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"deep-convolutional-denoising-of-low-light","repo_url":"https://github.com/TalRemez/deep_class_aware_denoising","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"deep-convolutional-denoising-of-low-light","repo_url":"https://github.com/isVoid/DenoiseNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"deep-convolutional-denoising-of-low-light","repo_url":"https://github.com/IshaFaodail/DeepCNN_denoising","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"astronomy","task_name":"Astronomy"},{"task_slug":"denoising","task_name":"Denoising"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1701.01687","atlas_url":"https://app.syntology.ai/?focus=1701.01687","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}